Statistics Seminars: An extensible software platform for the development and evaluation of Machine Learning methods
31 August 2009 14:15 in CM107
The implementation and evaluation of new machine-learning methods is a cumbersome task. New machine-learning proposals should be evaluated with a wide range of benchmark datasets and compare against some of the state-of-the-art algorithms in order to empirically show the performance of new proposed methods. This task can become a burdensome and time-consuming task if we have to design, develop and test all data structures and algorithms which are needed to implement and evaluate any machine-learning method. Time and memory efficiency issues often arise when this software is developed.
Weka is an open-source java software equipped with a wide range of facilities that ease the implementation and evaluation of new machine-learning methods. In this talk, the main features of this highly cited software will be highlighted. Moreover, it will be detailed a case study with the implementation and evaluation of simple credal decision trees.
Contact firstname.lastname@example.org for more information